INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

=>

-0.90

=-=-

-0.79

âĨĳ

-0.77

>[

-0.73

izoph

-0.73

late

-0.73

)=(

-0.72

ndum

-0.71

actionDate

-0.70

VILLE

-0.70

POSITIVE LOGITS

Os

0.68

Ps

0.67

Es

0.66

 seals

0.64

aer

0.63

 credits

0.63

 immersion

0.61

 demons

0.61

heon

0.60

Fen

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.